CN113987206A - Abnormal user identification method, device, equipment and storage medium - Google Patents

Abstract

The invention relates to big data technology, and discloses a method for identifying abnormal users, which includes: collecting historical complaint work order information, extracting appeal details, and obtaining appeal detail texts of multiple users; extracting key elements in each appeal detail text and generate the first abnormal user set based on the keywords; obtain the equipment information of multiple users based on the historical complaint ticket information, and generate the equipment information according to the equipment information of multiple users and preset equipment information conditions A second abnormal user set; obtaining a user knowledge graph constructed based on user information, identifying and generating a third abnormal user set from the user knowledge graph, and obtaining an abnormal user set. In addition, the present invention also relates to the blockchain technology, and the historical complaint work order information can be stored in the nodes of the blockchain. The invention also provides an abnormal user identification device, an electronic device and a storage medium. The invention can improve the identification efficiency of abnormal users.

Description

Identification method, device, equipment and storage medium of abnormal user

technical field

The present invention relates to the technical field of big data, and in particular, to a method, device, electronic device and computer-readable storage medium for identifying abnormal users.

Background technique

With the development of society, people have higher and higher requirements for the quality of life, and higher and higher requirements for various services. Once there is dissatisfaction, complaints will arise. For example, some customers complain to the bank because they are dissatisfied with the bank's service attitude and charging problems. However, some abnormal users maliciously complained to the bank in order to achieve their own economic goals, defaulting on repayment, or even not repaying, and entrusting a third party to complain to the bank, which may seriously affect the normal business of the bank.

For such abnormal users, at present, the main method is to manually check the content of the work order, listen to the recording, and determine whether it is a black user. This method is time-consuming, labor-intensive, inefficient and has a high error rate. Therefore, an efficient and effective method is needed. method for identifying abnormal users.

SUMMARY OF THE INVENTION

The present invention provides a method, device and computer-readable storage medium for identifying abnormal users, the main purpose of which is to improve the identification efficiency of abnormal users.

In order to achieve the above purpose, a method for identifying an abnormal user provided by the present invention includes:

Collect historical complaint work order information, extract appeal details from the historical complaint work order information, and obtain the appeal details texts of multiple users;

Extracting keywords in each of the appeal details texts, and generating a first abnormal user set based on the keywords;

Obtain the device information of a plurality of the users based on the historical complaint ticket information, and generate a second abnormal user set according to the device information of the plurality of users and a preset device information condition;

Obtain a user knowledge graph constructed based on user information, identify and generate a third abnormal user set from the user knowledge graph according to the first abnormal user set and the second abnormal user set, and combine with the first abnormal user set . The second abnormal user set is aggregated to obtain the abnormal user set.

Optionally, the extracting keywords in each of the appeal detail texts includes:

Divide each of the appeal detail texts into words to obtain a word set corresponding to each of the appeal detail texts;

calculating the term frequency and reverse file frequency for each term in each said term set;

Calculate the weight of each word according to the word frequency and the reverse document frequency;

The words in each of the word sets are sorted according to the weight from large to small, and words with a preset threshold number before the ranking are selected to obtain the keywords in each of the appeal detail texts.

Optionally, the calculating the word frequency of each word in each of the word sets includes:

Count the number of occurrences of each word in the corresponding appeal detail text to obtain the number of occurrences;

Count the number of all words in the word set to obtain the total number of words;

According to the number of occurrences and the total number of words, a preset first formula is used to generate the word frequency of each word.

Optionally, the calculating the reverse file frequency of each word in each of the word sets includes:

Count the total number of appeal detail texts corresponding to the word set to obtain the total number of documents;

For each word in the word set, count the number of appeal detail texts containing the word to obtain the number of documents containing the entry;

According to the total number of documents and the number of documents containing terms, a preset second formula is used to calculate and generate the reverse file frequency of each term.

Optionally, the device information includes one or more of account information, power, and number of pictures of the device used when the user submits the complaint work order. The condition generates a second set of abnormal users, including:

If any device information in the device information of the multiple users satisfies the preset device information conditions, the user corresponding to the device information is determined as an abnormal user, and all the determined abnormal users form a second abnormal user set .

Optionally, before the acquiring the user knowledge graph constructed based on the user information, the method further includes:

Take each of the users as an entity, and take the entity as a node of the knowledge graph;

Extracting the user information in the historical complaint ticket information as the attributes of each entity;

Analyzing the association relationship between the entities, and constructing a plurality of triples according to the attributes of the entities and the association relationship between the entities;

The multiple triples are visualized to obtain a user knowledge graph.

Optionally, the third abnormal user set is identified and generated from the user knowledge graph according to the first abnormal user set and the second abnormal user set, and is combined with the first abnormal user set and the first abnormal user set. Second, the abnormal user set is aggregated to obtain the abnormal user set, including:

marking the users in the first abnormal user set and the second abnormal user set in the user knowledge graph;

Find other users in the user knowledge graph who have the same phone attribute as the abnormal users in the first abnormal user set and the second abnormal user set, mark the remaining users as abnormal users, and obtain a third abnormal user user set;

The first abnormal user set, the second abnormal user set and the third abnormal user set are aggregated to obtain the abnormal user set, and the users of the abnormal user set are transferred.

In order to solve the above problems, the present invention also provides a device for identifying abnormal users, the device comprising:

The text collection module collects historical complaint work order information, extracts the appeal details from the historical complaint work order information, and obtains the appeal details texts of multiple users;

A keyword extraction module, used for extracting keywords in each of the appeal details texts, and generating a first abnormal user set based on the keywords;

a device information acquisition module, configured to acquire device information of a plurality of the users based on the historical complaint work order information, and generate a second abnormal user set according to the device information of the plurality of users and preset device information conditions;

The abnormal user generation module is used to obtain a user knowledge graph constructed based on user information, identify and generate a third abnormal user set from the user knowledge graph according to the first abnormal user set and the second abnormal user set, and combine with the user knowledge graph. The first abnormal user set and the second abnormal user set are aggregated to obtain the abnormal user set.

In order to solve the above problems, the present invention also provides an electronic device, the electronic device includes:

at least one processor; and,

a memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor, so that the at least one processor can execute the above-mentioned method for identifying an abnormal user .

In order to solve the above problems, the present invention also provides a computer-readable storage medium, where at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is executed by a processor in an electronic device to realize the above-mentioned The method for identifying abnormal users described above.

The embodiment of the present invention extracts appeal details from historical complaint work order information to ensure the integrity of the information; keywords are extracted from the appeal details text, and the first abnormal user is identified by matching the keywords with the preconfigured rules, and at the same time Identifying the second abnormal user through the device information can reduce the time spent on viewing the detailed text of the appeal and effectively improve the efficiency; the user knowledge graph is constructed based on the user information, and the user is directly taken as an entity, which is more intuitive and clear, and facilitates the acquisition of abnormal user information. Therefore, the method, device, electronic device and computer-readable storage medium for identifying abnormal users proposed by the present invention can improve the identification efficiency of abnormal users.

Description of drawings

1 is a schematic flowchart of a method for identifying an abnormal user according to an embodiment of the present invention;

2 is a schematic flowchart of extracting keywords according to an embodiment of the present invention;

3 is a functional block diagram of a device for identifying an abnormal user provided by an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of an electronic device implementing the method for identifying an abnormal user according to an embodiment of the present invention.

The realization, functional characteristics and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments.

Detailed ways

It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

The embodiment of the present application provides a method for identifying an abnormal user. The execution body of the method for identifying an abnormal user includes, but is not limited to, at least one of electronic devices that can be configured to execute the method provided by the embodiments of the present application, such as a server and a terminal. In other words, the method for identifying the abnormal user may be executed by software or hardware installed on the terminal device or the server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server can be an independent server, or can provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery network (Content Delivery Network) Network, CDN), and cloud servers for basic cloud computing services such as big data and artificial intelligence platforms.

Referring to FIG. 1 , it is a schematic flowchart of a method for identifying an abnormal user according to an embodiment of the present invention. In this embodiment, the method for identifying the abnormal user includes:

S1. Collect historical complaint work order information, extract appeal details from the historical complaint work order information, and obtain appeal detail texts of multiple users.

In the embodiment of the present invention, the historical complaint work order information is the complaint information submitted by the user due to dissatisfaction in various business scenarios, such as dissatisfaction with the bank's response or processing result, etc. The historical complaint work order information includes: But not limited to name, gender, phone number, ID number, card number, appeal details, and recording. In the embodiment of the present invention, the historical complaint work order information can be acquired from a preset background database.

Optionally, in order to further ensure the privacy and security of the historical complaint work order information, the historical complaint work order information may also be obtained from a node of a blockchain.

Further, the embodiment of the present invention extracts the text data corresponding to the claim detail field from the historical complaint work order information, and obtains a plurality of claim detail texts.

In one embodiment of the present invention, the request detail text corresponding to each user can be extracted from the historical complaint work order information according to the user's certificate number, so as to obtain the request detail text corresponding to multiple users.

Optionally, in this embodiment of the present invention, the complaint details of each complaint work order may be extracted from the historical complaint work order information, and the content of the complaint details may be classified and sorted according to the user name, so as to obtain the request details text corresponding to multiple users.

S2. Extract keywords in each of the appeal detail texts, and generate a first abnormal user set based on the keywords.

In the embodiment of the present invention, a related word extraction algorithm is used to extract keywords in each of the appeal detail texts, wherein the keyword extraction algorithm is a weighting technology used for information retrieval and data mining, and can be used to mine the key words in the article. words, such as the TF-IDF (term frequency–inverse document frequency) algorithm.

In detail, referring to FIG. 2 , the extracting keywords in each of the appeal detail texts includes:

S21. Divide each appeal detail text into words, and obtain a word set corresponding to each appeal detail text;

S22, calculating the word frequency and reverse file frequency of each word in each of the word sets;

S23, calculate the weight of each word according to the word frequency and the reverse file frequency;

S24. Sort the words in each of the word sets according to the weight from large to small, and select words with a preset threshold number before the ranking to obtain keywords in each of the appeal detail texts.

In one embodiment of the present invention, the stammering word segmentation method can be used to segment each of the appeal detail texts into words.

Further, the term frequency (TF) represents the frequency of words (keywords) appearing in the text. The inverse document frequency (IDF) is the IDF of a specific word, which is obtained by dividing the total number of documents by the number of documents containing the word, and then taking the logarithm of the obtained quotient; the less the number of documents containing the word, the greater the IDF. If it is large, it means that the entry has a good ability to distinguish between categories.

Specifically, the calculating the word frequency of each word in each of the word sets includes:

Count the number of occurrences of each word in the corresponding appeal detail text to obtain the number of occurrences;

Count the number of all words in the word set to obtain the total number of words;

According to the number of occurrences and the total number of words, a preset first formula is used to generate the word frequency of each word.

Wherein, the preset first formula is: TF(c)=the number of occurrences of word c/total number of words.

Further, the calculating the reverse file frequency of each word in each of the word sets includes:

Count the total number of appeal detail texts corresponding to the word set to obtain the total number of documents;

For each word in the word set, count the number of appeal detail texts containing the word to obtain the number of documents containing the entry;

According to the total number of documents and the number of documents containing terms, a preset second formula is used to calculate and generate the reverse file frequency of each term.

The preset second formula is: IDF(c)=log(the total number of documents/the number of documents containing a term containing the word c+1).

Further, the embodiment of the present invention calculates the weight of each word according to the following formula: TF-IDF=word frequency (TF)*inverse document frequency (IDF).

In detail, the generating the first abnormal user set based on the keyword includes:

Get the preset template keywords;

Matching each keyword of the appeal details text with the template keyword to obtain a matching result;

If the matching result is consistent, the user corresponding to the keyword is marked as an abnormal user to obtain a first abnormal user set.

The template keywords are words commonly used by abnormal users when making complaints, such as threats, filing a case, and the like. The matching results include matching and complete non-matching. After extracting and matching keywords from all historical complaint ticket information, extracting all the users marked as abnormal users, the first abnormal user set can be obtained.

For example, after a user submits the complaint work order information, the keywords extracted from the complaint work order information include bad attitude, alarm, and threat. Among them, "threat" is exactly the same as the keyword in the template keyword. The matching result is consistent, and the user corresponding to the current complaint ticket information is marked as an abnormal user.

S3. Acquire device information of a plurality of the users based on the historical complaint ticket information, and generate a second abnormal user set according to the device information of the plurality of users and a preset device information condition.

In the embodiment of the present invention, the user equipment information refers to the relevant information of the equipment used by the user when logging in to the system to make a complaint, including but not limited to account information, power, and number of pictures of the equipment used by the user when submitting a complaint work order. When a user submits a complaint ticket, the user can obtain and save relevant information about the user's use of the device through preset permissions.

Further, generating a second abnormal user set according to the device information of multiple users and preset device information conditions, including:

If any device information in the device information of the multiple users satisfies the preset device information conditions, the user corresponding to the device information is determined as an abnormal user, and all the determined abnormal users form a second abnormal user set .

The preset device information conditions include but are not limited to: multiple accounts have been logged in the same device; the power of the device has not changed; the number of pictures in the device is zero.

Under normal circumstances, users only use one account, and the time to log in to the system is not fixed, and the power of the device is also not fixed. If an account makes a complaint, or uses some malicious complaint software, the device information obtained is virtual, the obtained device power is a constant value, and the number of pictures is also 0. Therefore, it can be judged by the device information whether it is an abnormal user.

S4. Acquire a user knowledge graph constructed based on user information, identify and generate a third abnormal user set from the user knowledge graph according to the first abnormal user set and the second abnormal user set, and generate a third abnormal user set with the first abnormal user set. The user set and the second abnormal user set are aggregated to obtain the abnormal user set.

In this embodiment of the present invention, the user information includes, but is not limited to, name, gender, phone number, certificate number, card number, and the like.

In detail, before the acquiring and constructing a knowledge graph based on user information, the method further includes:

Take each of the users as an entity, and take the entity as a node of the knowledge graph;

Extracting the user information in the historical complaint ticket information as the attributes of each entity;

Analyzing the association relationship between the entities, and constructing a plurality of triples according to the attributes of the entities and the association relationship between the entities;

The multiple triples are visualized to obtain a user knowledge graph.

The analysis of the association relationship between the entities in the embodiment of the present invention is based on data mining technology to perform association mining on the entity data. If two users have the same attribute value (telephone number), it means that the two users relationship between them.

The triple can be represented as "(A, B, C)", where B is a relationship, and A and C are graph nodes, for example, between user A and user B, which is represented by a triple as "( User A, Association, User C)".

Further, the third abnormal user set is identified and generated from the user knowledge graph according to the first abnormal user set and the second abnormal user set, and is combined with the first abnormal user set and the second abnormal user set. The abnormal user set is aggregated to obtain the abnormal user set, including:

marking the users in the first abnormal user set and the second abnormal user set in the user knowledge graph;

Find other users with the same phone attribute as the abnormal users in the first abnormal user set and the second abnormal user set in the user knowledge graph, mark the remaining users as abnormal users, and obtain a third abnormal user set;

The first abnormal user set, the second abnormal user set and the third abnormal user set are aggregated to obtain the abnormal user set, and the users of the abnormal user set are transferred.

The embodiment of the present invention can identify abnormal customers in batches, reduce the difficulty of identification by staff, improve the identification efficiency, and make further coping strategies for abnormal customers, such as handing over to corresponding agencies for processing, reducing group complaints, public opinion and other aspects. risk.

The embodiment of the present invention extracts appeal details from historical complaint work order information to ensure the integrity of the information; keywords are extracted from the appeal details text, and the first abnormal user is identified by matching the keywords with the preconfigured rules, and at the same time Identifying the second abnormal user through the device information can reduce the time spent on viewing the detailed text of the appeal and effectively improve the efficiency; the user knowledge graph is constructed based on the user information, and the user is directly taken as an entity, which is more intuitive and clear, and facilitates the acquisition of abnormal user information. Therefore, the method, device, electronic device and computer-readable storage medium for identifying abnormal users proposed by the present invention can improve the identification efficiency of abnormal users.

As shown in FIG. 3 , it is a functional block diagram of a device for identifying an abnormal user provided by an embodiment of the present invention.

The apparatus 100 for identifying an abnormal user according to the present invention may be installed in an electronic device. According to the realized functions, the abnormal user identification device 100 may include a text collection module 101 , a keyword extraction module 102 , a device information acquisition module 103 and an abnormal user generation module 104 . The modules in the present invention can also be called units, which refer to a series of computer program segments that can be executed by the electronic device processor and can perform fixed functions, and are stored in the memory of the electronic device.

In this embodiment, the functions of each module/unit are as follows:

In the text collection module 101, the user collects historical complaint work order information, extracts the appeal details from the historical complaint work order information, and obtains the appeal details texts of multiple users.

In the embodiment of the present invention, the historical complaint work order information is the complaint information submitted by the user due to dissatisfaction in various business scenarios, such as dissatisfaction with the bank's response or processing result, etc. The historical complaint work order information includes: But not limited to name, gender, phone number, ID number, card number, appeal details, and recording. In the embodiment of the present invention, the historical complaint work order information can be acquired from a preset background database.

Further, the embodiment of the present invention extracts the text data corresponding to the claim detail field from the historical complaint work order information, and obtains a plurality of claim detail texts.

The keyword extraction module 102 is configured to extract keywords in each of the appeal detail texts through a keyword extraction algorithm, and generate a first abnormal user set based on the keywords.

In the embodiment of the present invention, a related word extraction algorithm is used to extract keywords in each of the appeal detail texts, wherein the keyword extraction algorithm is a weighting technology used for information retrieval and data mining, and can be used to mine the key words in the article. words, such as the TF-IDF (term frequency–inverse document frequency) algorithm.

In detail, the keyword extraction module 102 is specifically used for:

Divide each of the appeal detail texts into words to obtain a word set corresponding to each of the appeal detail texts;

calculating the term frequency and reverse file frequency for each term in each said term set;

Calculate the weight of each word according to the word frequency and the reverse document frequency;

The words in each of the word sets are sorted according to the weight from large to small, and words with a preset threshold number before the ranking are selected to obtain the keywords in each of the appeal detail texts.

Specifically, the calculating the word frequency of each word in each of the word sets includes:

Count the number of occurrences of each word in the corresponding appeal detail text to obtain the number of occurrences;

Count the number of all words in the word set to obtain the total number of words;

According to the number of occurrences and the total number of words, a preset first formula is used to generate the word frequency of each word.

Wherein, the preset first formula is: TF(c)=the number of occurrences of word c/total number of words.

Further, the calculating the reverse file frequency of each word in each of the word sets includes:

Count the total number of appeal detail texts corresponding to the word set to obtain the total number of documents;

For each word in the word set, count the number of appeal detail texts containing the word to obtain the number of documents containing the entry;

According to the total number of documents and the number of documents containing terms, a preset second formula is used to calculate and generate the reverse file frequency of each term.

The preset second formula is: IDF(c)=log(the total number of documents/the number of documents containing a term containing the word c+1).

Further, the embodiment of the present invention calculates the weight of each word according to the following formula: TF-IDF=word frequency (TF)*inverse document frequency (IDF).

In detail, the generating the first abnormal user set based on the keyword includes:

Get the preset template keywords;

Matching each keyword of the appeal details text with the template keyword to obtain a matching result;

If the matching result is consistent, the user corresponding to the keyword is marked as an abnormal user to obtain a first abnormal user set.

The device information obtaining module 103 is configured to obtain the device information of a plurality of the users based on the historical complaint work order information, and generate a second abnormal user set according to the device information of the plurality of users and a preset device information condition. .

In the embodiment of the present invention, the user equipment information refers to the relevant information of the equipment used by the user when logging in to the system to make a complaint, including but not limited to account information, power, and number of pictures of the equipment used by the user when submitting a complaint work order. When a user submits a complaint ticket, the user can obtain and save relevant information about the user's use of the device through preset permissions.

Further, the device information acquisition module 103 is specifically configured to: if any device information in the device information of the multiple users satisfies the preset device information condition, determine the user corresponding to the any device information as abnormal Users, it is determined that all abnormal users obtained form a second abnormal user set.

The preset device information conditions include but are not limited to: multiple accounts have been logged in the same device; the power of the device has not changed; the number of pictures in the device is zero.

The abnormal user generation module 104 is configured to obtain a user knowledge graph constructed based on user information, and identify and generate a third abnormal user set from the user knowledge graph according to the first abnormal user set and the second abnormal user set. , and aggregated with the first abnormal user set and the second abnormal user set to obtain the abnormal user set.

In this embodiment of the present invention, the user information includes, but is not limited to, name, gender, phone number, certificate number, card number, and the like.

In detail, the abnormal user generation module 104 is specifically used for:

marking the users in the first abnormal user set and the second abnormal user set in the user knowledge graph;

Find other users with the same phone attribute as the abnormal users in the first abnormal user set and the second abnormal user set in the user knowledge graph, mark the remaining users as abnormal users, and obtain a third abnormal user set;

The first abnormal user set, the second abnormal user set and the third abnormal user set are aggregated to obtain the abnormal user set, and the users of the abnormal user set are transferred.

As shown in FIG. 4 , it is a schematic structural diagram of an electronic device implementing a method for identifying an abnormal user provided by an embodiment of the present invention.

The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as an abnormal user's identification program.

The processor 10 may be composed of integrated circuits in some embodiments, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits packaged with the same function or different functions, including one or A combination of multiple central processing units (Central Processing Units, CPUs), microprocessors, digital processing chips, graphics processors, and various control chips, etc. The processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, and by running or executing the program or module stored in the memory 11 (for example, abnormal execution) User identification program, etc.), and call data stored in the memory 11 to perform various functions of the electronic device and process data.

The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. . In some embodiments, the memory 11 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 may also be an external storage device of the electronic device, such as a pluggable mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) equipped on the electronic device. ) card, flash card (Flash Card) and so on. Further, the memory 11 may also include both an internal storage unit of an electronic device and an external storage device. The memory 11 can not only be used to store application software installed in the electronic device and various data, such as codes of abnormal user identification programs, etc., but also can be used to temporarily store data that has been output or will be output.

The communication bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus or the like. The bus can be divided into address bus, data bus, control bus and so on. The bus is configured to implement connection communication between the memory 11 and at least one processor 10 and the like.

The communication interface 13 is used for communication between the above electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (eg, a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, and the like. The display may also be appropriately called a display screen or a display unit, which is used for displaying information processed in the electronic device and for displaying a visual user interface.

FIG. 4 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 4 does not constitute a limitation on the electronic device 1, and may include fewer or more components than those shown in the drawings. components, or a combination of certain components, or a different arrangement of components.

For example, although not shown, the electronic device may also include a power source (such as a battery) for powering the various components, preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device Implement functions such as charge management, discharge management, and power management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components. The electronic device may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

It should be understood that the embodiments are only used for illustration, and are not limited by this structure in the scope of the patent application.

The abnormal user identification program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions, and when running in the processor 10, it can realize:

Collect historical complaint work order information, extract appeal details from the historical complaint work order information, and obtain the appeal details texts of multiple users;

Extracting keywords in each of the appeal details texts, and generating a first abnormal user set based on the keywords;

Obtain the device information of a plurality of the users based on the historical complaint ticket information, and generate a second abnormal user set according to the device information of the plurality of users and a preset device information condition;

Obtain a user knowledge graph constructed based on user information, identify and generate a third abnormal user set from the user knowledge graph according to the first abnormal user set and the second abnormal user set, and combine with the first abnormal user set . The second abnormal user set is aggregated to obtain the abnormal user set.

Specifically, for the specific implementation method of the above-mentioned instruction by the processor 10, reference may be made to the description of the relevant steps in the embodiment corresponding to the accompanying drawings, which will not be repeated here.

Further, if the modules/units integrated in the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. The computer-readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM, Read-Only). Memory).

The present invention also provides a computer-readable storage medium, where the readable storage medium stores a computer program, and when executed by a processor of an electronic device, the computer program can realize:

Collect historical complaint work order information, extract appeal details from the historical complaint work order information, and obtain the appeal details texts of multiple users;

Extracting keywords in each of the appeal details texts, and generating a first abnormal user set based on the keywords;

Obtain the device information of a plurality of the users based on the historical complaint ticket information, and generate a second abnormal user set according to the device information of the plurality of users and a preset device information condition;

Obtain a user knowledge graph constructed based on user information, identify and generate a third abnormal user set from the user knowledge graph according to the first abnormal user set and the second abnormal user set, and combine with the first abnormal user set . The second abnormal user set is aggregated to obtain the abnormal user set. .

In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the modules is only a logical function division, and there may be other division manners in actual implementation.

The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software function modules.

It will be apparent to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, but that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics of the invention.

Therefore, the embodiments are to be regarded in all respects as illustrative and not restrictive, and the scope of the invention is to be defined by the appended claims rather than the foregoing description, which are therefore intended to fall within the scope of the claims. All changes within the meaning and range of the equivalents of , are included in the present invention. Any reference signs in the claims shall not be construed as limiting the involved claim.

The blockchain referred to in the present invention is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

The embodiments of the present application may acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. .

Furthermore, it is clear that the word "comprising" does not exclude other units or steps and the singular does not exclude the plural. Several units or means recited in the system claims can also be realized by one unit or means by means of software or hardware. The words first, second, etc. are used to denote names and do not denote any particular order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be Modifications or equivalent substitutions can be made without departing from the spirit and scope of the technical solutions of the present invention.

Claims (10)

1. A method for identifying an abnormal user, the method comprising:

collecting historical complaint work order information, and extracting complaint details from the historical complaint work order information to obtain complaint detail texts of a plurality of users;

extracting keywords in each appeal detail text, and generating a first abnormal user set based on the keywords;

acquiring equipment information of a plurality of users based on the historical complaint work order information, and generating a second abnormal user set according to the equipment information of the users and preset equipment information conditions;

acquiring a user knowledge graph constructed based on user information, identifying and generating a third abnormal user set from the user knowledge graph according to the first abnormal user set and the second abnormal user set, and summarizing the third abnormal user set, the first abnormal user set and the second abnormal user set to obtain an abnormal user set.

2. The method for identifying an abnormal user according to claim 1, wherein the extracting the keyword in each of the appeal detail texts comprises:

segmenting each appeal detail text into words to obtain a word set corresponding to each appeal detail text;

calculating the word frequency and the reverse file frequency of each word in each word set;

calculating the weight of each word according to the word frequency and the reverse file frequency;

and sequencing the words in each word set from large to small according to the weight, and selecting words with a preset threshold number before ranking to obtain the keywords in each appeal detail text.

3. The method for identifying abnormal users as claimed in claim 2, wherein said calculating the word frequency of each word in each said word set comprises:

respectively counting the occurrence frequency of each word in the corresponding appeal detail text to obtain the occurrence frequency;

counting the number of all words in the word set to obtain the total number of words;

and generating the word frequency of each word by using a preset first formula according to the occurrence times and the total word quantity.

4. The method for identifying abnormal users according to claim 2, wherein said calculating a reverse document frequency of each term in each of said term sets comprises:

counting the total number of appeal detail texts corresponding to the word set to obtain the total document number;

counting the number of appeal detail texts containing the words for each word in the word set to obtain the number of documents containing entries;

and calculating and generating the reverse file frequency of each term by using a preset second formula according to the total document quantity and the quantity of the documents containing the terms.

5. The method for identifying an abnormal user according to claim 1, wherein the device information includes at least one of account information, electric quantity, and number of pictures of a device used when the user submits a complaint work order, and the generating of the second abnormal user set according to the device information of the plurality of users and a preset device information condition includes:

if any piece of equipment information in the pieces of equipment information of the users meets a preset equipment information condition, judging the user corresponding to the any piece of equipment information as an abnormal user, and determining that all the obtained abnormal users form a second abnormal user set.

6. The method for identifying abnormal users according to claim 1, wherein before the obtaining of the user knowledge graph constructed based on the user information, the method further comprises:

taking each user as an entity, and taking the entity as a node of the knowledge graph;

extracting user information in the historical complaint work order information as attributes of each entity;

analyzing the incidence relation among the entities, and constructing a plurality of triples according to the attributes of the entities and the incidence relation among the entities;

and visualizing the triples to obtain the user knowledge graph.

7. The method for identifying abnormal users according to any one of claims 1 to 6, wherein the identifying and generating a third abnormal user set from the user knowledge graph according to the first abnormal user set and the second abnormal user set, and summarizing the third abnormal user set with the first abnormal user set and the second abnormal user set to obtain an abnormal user set comprises:

tagging users in the first and second abnormal user sets in the user knowledge graph;

searching other users having the same telephone attributes with the abnormal users in the first abnormal user set and the second abnormal user set in the user knowledge graph, and marking the other users as abnormal users to obtain a third abnormal user set;

and summarizing the first abnormal user set, the second abnormal user set and the third abnormal user set to obtain an abnormal user set, and performing transfer processing on the users of the abnormal user set.

8. An apparatus for identifying an abnormal user, the apparatus comprising:

the text collection module is used for collecting historical complaint work order information and extracting complaint details from the historical complaint work order information to obtain complaint detail texts of a plurality of users;

the keyword extraction module is used for extracting keywords in each appeal detail text and generating a first abnormal user set based on the keywords;

the equipment information acquisition module is used for acquiring equipment information of a plurality of users based on the historical complaint work order information and generating a second abnormal user set according to the equipment information of the users and preset equipment information conditions;

and the abnormal user generation module is used for acquiring a user knowledge graph constructed based on user information, identifying and generating a third abnormal user set from the user knowledge graph according to the first abnormal user set and the second abnormal user set, and summarizing the third abnormal user set, the first abnormal user set and the second abnormal user set to obtain an abnormal user set.

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of identifying an anomalous user as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements a method for identifying an anomalous user in accordance with any one of claims 1 to 7.

Images